dvgodoy

true_b = 1
true_w = 2
N = 100

# Data Generation
np.random.seed(42)
x = np.random.rand(N, 1)
epsilon = (.1 * np.random.randn(N, 1))
y = true_b + true_w * x + epsilon

dvgodoy

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler(with_mean=True, with_std=True)
# We use the TRAIN set ONLY to fit the scaler
scaler.fit(x_train)

# Now we can use the already fit scaler to TRANSFORM
# both TRAIN and VALIDATION sets
scaled_x_train = scaler.transform(x_train)
scaled_x_val = scaler.transform(x_val)

dvgodoy

# Generates train and validation sets
# It uses the same train_idx and val_idx as before,
# but it applies to bad_x

bad_x_train, y_train = bad_x[train_idx], y[train_idx]
bad_x_val, y_val = bad_x[val_idx], y[val_idx]

dvgodoy

true_b = 1
true_w = 2
N = 100

# Data Generation
np.random.seed(42)

# We divide w by 10
bad_w = true_w / 10
# And multiply x by 10

dvgodoy

losses = []
val_losses = []
train_step = make_train_step(model, loss_fn, optimizer)

for epoch in range(n_epochs):
    for x_batch, y_batch in train_loader:
        x_batch = x_batch.to(device)
        y_batch = y_batch.to(device)

        loss = train_step(x_batch, y_batch)

dvgodoy

losses = []
train_step = make_train_step(model, loss_fn, optimizer)

for epoch in range(n_epochs):
    for x_batch, y_batch in train_loader:
        # the dataset "lives" in the CPU, so do our mini-batches
        # therefore, we need to send those mini-batches to the
        # device where the model "lives"
        x_batch = x_batch.to(device)
        y_batch = y_batch.to(device)

dvgodoy

def make_train_step(model, loss_fn, optimizer):
    # Builds function that performs a step in the train loop
    def train_step(x, y):
        # Sets model to TRAIN mode
        model.train()
        # Makes predictions
        yhat = model(x)
        # Computes loss
        loss = loss_fn(y, yhat)
        # Computes gradients

dvgodoy

torch.manual_seed(42)

x_tensor = torch.from_numpy(x).float()
y_tensor = torch.from_numpy(y).float()

# Builds dataset with ALL data
dataset = TensorDataset(x_tensor, y_tensor)
# Splits randomly into train and validation datasets
train_dataset, val_dataset = random_split(dataset, [80, 20])

dvgodoy

from torch.utils.data.dataset import random_split

x_tensor = torch.from_numpy(x).float()
y_tensor = torch.from_numpy(y).float()

dataset = TensorDataset(x_tensor, y_tensor)

train_dataset, val_dataset = random_split(dataset, [80, 20])

train_loader = DataLoader(dataset=train_dataset, batch_size=16)

dvgodoy

from torch.utils.data.sampler import SubsetRandomSampler

train_sampler = SubsetRandomSampler(train_idx)
val_sampler = SubsetRandomSampler(val_idx)

x_tensor = torch.from_numpy(x).float()
y_tensor = torch.from_numpy(y).float()

dataset = TensorDataset(x_tensor, y_tensor)